hydai/ gpt-oss-120b-mandarin-thinking

182 Downloads Updated 7 months ago

Converted to MXFP4_MOE from https://huggingface.co/FreeSEED-AI/gpt-oss-120b-mandarin-thinking

tools thinking

ollama run hydai/gpt-oss-120b-mandarin-thinking

curl http://localhost:11434/api/chat \
  -d '{
    "model": "hydai/gpt-oss-120b-mandarin-thinking",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

from ollama import chat

response = chat(
    model='hydai/gpt-oss-120b-mandarin-thinking',
    messages=[{'role': 'user', 'content': 'Hello!'}],
)
print(response.message.content)

import ollama from 'ollama'

const response = await ollama.chat({
  model: 'hydai/gpt-oss-120b-mandarin-thinking',
  messages: [{role: 'user', content: 'Hello!'}],
})
console.log(response.message.content)

Applications

Claude Code

Claude Code ollama launch claude --model hydai/gpt-oss-120b-mandarin-thinking

Codex

Codex ollama launch codex --model hydai/gpt-oss-120b-mandarin-thinking

OpenCode

OpenCode ollama launch opencode --model hydai/gpt-oss-120b-mandarin-thinking

OpenClaw

OpenClaw ollama launch openclaw --model hydai/gpt-oss-120b-mandarin-thinking

Models

Name

1 model

Size

Context

Input

gpt-oss-120b-mandarin-thinking:latest

63GB · 128K context window · Text · 7 months ago

gpt-oss-120b-mandarin-thinking:latest

63GB

128K

Text

Readme

GPT-OSS-ZhTW-Thinking-MXFP4-MOE-GGUF

A specialized language model optimized for thinking in Traditional Chinese (Taiwanese Mandarin).

This is a quantized GGUF version of the GPT-OSS-ZhTW-Thinking model.

Converted via llama.cpp b6316

🌟 Key Features

Native Taiwanese Mandarin Thinking: Default reasoning and thinking patterns optimized for Traditional Chinese
Enhanced Cultural Understanding: Deep comprehension of Taiwanese cultural contexts, idioms, and social nuances
GPT-based Architecture: Standard GPT-OSS transformer architecture fine-tuned for zh-TW applications

📊 Model Specifications

Model Size: 120B parameters
Architecture: GPT-based MoE transformer
Training: Fine-tuned for Traditional Chinese (zh-TW)

🚀 Usage

Serving with vllm or sglang.

📝 License

This model is released under the Apache 2.0 License.

🤝 Contributing

We welcome contributions and feedback! Please open an issue or submit a pull request if you have suggestions for improvements.

Made with ❤️ by FreeSEED-AI

# GPT-OSS-ZhTW-Thinking-MXFP4-MOE-GGUF

[![Model on HuggingFace](https://img.shields.io/badge/🤗-HuggingFace-yellow.svg)](https://huggingface.co/FreeSEED-AI/gpt-oss-zhtw-thinking)
[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](LICENSE)

A specialized language model optimized for thinking in Traditional Chinese (Taiwanese Mandarin).

This is a quantized GGUF version of the [GPT-OSS-ZhTW-Thinking](https://huggingface.co/FreeSEED-AI/gpt-oss-120b-mandarin-thinking) model.

Converted via llama.cpp b6316

## 🌟 Key Features

- **Native Taiwanese Mandarin Thinking**: Default reasoning and thinking patterns optimized for Traditional Chinese
- **Enhanced Cultural Understanding**: Deep comprehension of Taiwanese cultural contexts, idioms, and social nuances
- **GPT-based Architecture**: Standard GPT-OSS transformer architecture fine-tuned for zh-TW applications

## 📊 Model Specifications

- **Model Size**: 120B parameters
- **Architecture**: GPT-based MoE transformer
- **Training**: Fine-tuned for Traditional Chinese (zh-TW)

## 🚀 Usage

Serving with [vllm](https://x.com/MaziyarPanahi/status/1955741905515323425) or [sglang](https://github.com/sgl-project/sglang/issues/8833).

## 📝 License

This model is released under the Apache 2.0 License.

## 🤝 Contributing

We welcome contributions and feedback! Please open an issue or submit a pull request if you have suggestions for improvements.

---

*Made with ❤️  by FreeSEED-AI*

Paste, drop or click to upload images (.png, .jpeg, .jpg, .svg, .gif)